Skip to content
Person logo

Person MCP server

Which MCP servers are Person's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.

read 2026-10-26

← Back to Person

Whose server it is
  • Registry namework.person/career-recordverified in the MCP registry

The registry name sits under person.work. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

When we asked itchecked 2026-10-26
  • Stateanswerschecked 2026-10-26
  • Tools4
  • Server calls itselfperson-work
  • Server version0.7.0
  • Protocol version2025-06-18

On 2026-10-26 the server answered initialize and tools/list without a sign-in. First answer in 1063 ms.

Should an agent connect itNot proven either way yet
  • Whether its tools do the product's job has not been judged yet.
  • Checked on 1 of the 7 days it takes to judge reliability.

Once connected

  • Parameters are untyped or undescribed in 3 of 4 tools: check arguments before calling.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

Measured dailydaily checks: 1, the first on 2026-10-27
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 1 so far
  • Answeredmeasuring1 of the 7 daily checks it takes to print a share
  • Median first answer1302 ms
  • Space in an agent's context≈ 2,757 tokensthe definitions of all its tools (4), which an agent carries on every turn
  • Tool definitionsB · 88 of 100
  • Typed results0 of 4 toolsdeclared outputSchema: results come typed, read once
  • Parameters without a description: in 3 of 4

Worth a look

None of the five warning signs in these definitions.

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

Tools it offers4 tools · read 2026-10-26
  • get_profile

    Returns one public Career Record whose owner explicitly enabled MCP visibility. Contact values are excluded.

  • sync_my_profile

    Explicit initial-import operation for structured facts already interpreted by the calling agent. It does not accept or store a raw CV, PDF, or source text, and person.work does not run a second AI interpretation. The operation…

  • get_my_career_record

    Returns the OAuth-authenticated owner's canonical record. Read this before proposing an ongoing CV update so stable experience identifiers and confirmed facts are preserved.

  • propose_my_career_change

    Adds a structured, human-readable diff to the owner's review inbox. Experience upserts may include a public HTTPS company_logo_url; person.work imports its own protected copy only after owner approval. Use this for normal maintenance…

How to connect

Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:

{
  "mcpServers": {
    "career-record": {
      "type": "http",
      "url": "https://person.work/api/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http person https://person.work/api/mcp

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://person.work/api/mcp as a custom connector in the settings.

Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.